Training in progress, epoch 1, checkpoint
Browse files- checkpoint-212/README.md +21 -0
- checkpoint-212/adapter_config.json +26 -0
- checkpoint-212/adapter_model.bin +3 -0
- checkpoint-212/optimizer.pt +3 -0
- checkpoint-212/rng_state.pth +3 -0
- checkpoint-212/scheduler.pt +3 -0
- checkpoint-212/sentencepiece.bpe.model +3 -0
- checkpoint-212/special_tokens_map.json +19 -0
- checkpoint-212/tokenizer.json +0 -0
- checkpoint-212/tokenizer_config.json +24 -0
- checkpoint-212/trainer_state.json +33 -0
- checkpoint-212/training_args.bin +3 -0
checkpoint-212/README.md
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- quant_method: bitsandbytes
|
9 |
+
- load_in_8bit: True
|
10 |
+
- load_in_4bit: False
|
11 |
+
- llm_int8_threshold: 6.0
|
12 |
+
- llm_int8_skip_modules: None
|
13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
14 |
+
- llm_int8_has_fp16_weight: False
|
15 |
+
- bnb_4bit_quant_type: fp4
|
16 |
+
- bnb_4bit_use_double_quant: False
|
17 |
+
- bnb_4bit_compute_dtype: float32
|
18 |
+
### Framework versions
|
19 |
+
|
20 |
+
|
21 |
+
- PEFT 0.5.0
|
checkpoint-212/adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "camembert/camembert-large",
|
4 |
+
"bias": "all",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 16,
|
11 |
+
"lora_dropout": 0.1,
|
12 |
+
"modules_to_save": [
|
13 |
+
"classifier.bias",
|
14 |
+
"classifier.weight"
|
15 |
+
],
|
16 |
+
"peft_type": "LORA",
|
17 |
+
"r": 64,
|
18 |
+
"revision": null,
|
19 |
+
"target_modules": [
|
20 |
+
"query",
|
21 |
+
"key",
|
22 |
+
"value",
|
23 |
+
"dense"
|
24 |
+
],
|
25 |
+
"task_type": "TOKEN_CLS"
|
26 |
+
}
|
checkpoint-212/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de8ce2bccb319d2bdfcd877592856a532a0375a6fdb46c6f0ffaa639260d8d42
|
3 |
+
size 115364125
|
checkpoint-212/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fbb85a32e61c7d4d1e1021c86fe0c961f148308dfdf0e396e22686d9856e5b3
|
3 |
+
size 230776198
|
checkpoint-212/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98e790dcbbbddab745dd1300b781df2ebfa1854145e6684d655d251f289b5684
|
3 |
+
size 14575
|
checkpoint-212/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:605c05828269613cb5866707586c2c342dd863c38ccde072ff12613b969d5903
|
3 |
+
size 627
|
checkpoint-212/sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f98f266fdc548c94216aaadc13ffaaafacf0c8793303e2195322d954549ea261
|
3 |
+
size 808767
|
checkpoint-212/special_tokens_map.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>NOTUSED",
|
4 |
+
"</s>NOTUSED"
|
5 |
+
],
|
6 |
+
"bos_token": "<s>",
|
7 |
+
"cls_token": "<s>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"mask_token": {
|
10 |
+
"content": "<mask>",
|
11 |
+
"lstrip": true,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<pad>",
|
17 |
+
"sep_token": "</s>",
|
18 |
+
"unk_token": "<unk>"
|
19 |
+
}
|
checkpoint-212/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-212/tokenizer_config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>NOTUSED",
|
4 |
+
"</s>NOTUSED"
|
5 |
+
],
|
6 |
+
"bos_token": "<s>",
|
7 |
+
"clean_up_tokenization_spaces": true,
|
8 |
+
"cls_token": "<s>",
|
9 |
+
"eos_token": "</s>",
|
10 |
+
"mask_token": {
|
11 |
+
"__type": "AddedToken",
|
12 |
+
"content": "<mask>",
|
13 |
+
"lstrip": true,
|
14 |
+
"normalized": true,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false
|
17 |
+
},
|
18 |
+
"model_max_length": 1000000000000000019884624838656,
|
19 |
+
"pad_token": "<pad>",
|
20 |
+
"sep_token": "</s>",
|
21 |
+
"sp_model_kwargs": {},
|
22 |
+
"tokenizer_class": "CamembertTokenizer",
|
23 |
+
"unk_token": "<unk>"
|
24 |
+
}
|
checkpoint-212/trainer_state.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 212,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"learning_rate": 0.000199,
|
14 |
+
"loss": 3.2614,
|
15 |
+
"step": 212
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"eval_loss": NaN,
|
20 |
+
"eval_runtime": 4.1946,
|
21 |
+
"eval_samples_per_second": 161.161,
|
22 |
+
"eval_steps_per_second": 20.264,
|
23 |
+
"step": 212
|
24 |
+
}
|
25 |
+
],
|
26 |
+
"logging_steps": 500,
|
27 |
+
"max_steps": 42400,
|
28 |
+
"num_train_epochs": 200,
|
29 |
+
"save_steps": 500,
|
30 |
+
"total_flos": 283175043047088.0,
|
31 |
+
"trial_name": null,
|
32 |
+
"trial_params": null
|
33 |
+
}
|
checkpoint-212/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:771d084b8daaadfbfc448be3f4420adca931f8c6583bdc3f881ade3e2af8ca6d
|
3 |
+
size 4155
|